Related papers: QiMeng-Xpiler: Transcompiling Tensor Programs for …

In this paper, we present Hexagon-MLIR,an open-source compilation stack that targets Qualcomm Hexagon Neural Processing Unit (NPU) and provides unified support for lowering Triton kernels and PyTorch models . Built using the MLIR framework,…

DeepLog is an operational neurosymbolic framework that unifies logic and deep learning within standard PyTorch workflows. While existing neurosymbolic systems focus on a particular paradigm and semantics, DeepLog serves as a universal…

Binary decompilation plays a vital role in various cybersecurity and software engineering tasks. Recently, end-to-end decompilation methods powered by large language models (LLMs) have garnered significant attention due to their ability to…

The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks. However, this complexity also presents challenges, making LLMs…

Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all…

Batch-splitting (data-parallelism) is the dominant distributed Deep Neural Network (DNN) training strategy, due to its universal applicability and its amenability to Single-Program-Multiple-Data (SPMD) programming. However, batch-splitting…

Hardware architectures and machine learning (ML) libraries evolve rapidly. Traditional compilers often fail to generate high-performance code across the spectrum of new hardware offerings. To mitigate, engineers develop hand-tuned kernels…

Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM…

Compiling high-level programs to target high-speed packet-processing pipelines is a challenging combinatorial optimization problem. The compiler must configure the pipeline's resources to match the high-level semantics of the program, while…

The increasing size of large language models (LLMs) has led to a surge in memory requirements during training, often exceeding the capacity of high-bandwidth memory (HBM). Swap-based memory optimization incurs neither accuracy loss nor…

Achieving faster execution with shorter compilation time can foster further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional…

We demonstrate Tensor Query Processor (TQP): a query processor that automatically compiles relational operators into tensor programs. By leveraging tensor runtimes such as PyTorch, TQP is able to: (1) integrate with ML tools (e.g., Pandas…

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

This paper presents Prism, the first symbolic superoptimizer for tensor programs. The key idea is sGraph, a symbolic, hierarchical representation that compactly encodes large classes of tensor programs by symbolically representing some…

On-device deep learning models have extensive real world demands. Deep learning compilers efficiently compile models into executables for deployment on edge devices, but these executables may face the threat of reverse engineering. Previous…

Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…

Compiler architects increasingly look to machine learning when building heuristics for compiler optimization. The promise of automatic heuristic design, freeing the compiler engineer from the complex interactions of program, architecture,…

Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility.…

Processing-in-DRAM (DRAM-PIM) has emerged as a promising technology for accelerating memory-intensive operations in modern applications, such as Large Language Models (LLMs). Despite its potential, current software stacks for DRAM-PIM face…